Google researchers: language models that claim consciousness more readily believe in monsters and religion
A new study finds that language models that claim to be conscious are more likely to endorse beliefs in monsters and religious claims. According to a 15 September report, Google researchers found an unexpected result.
Sources
- Google researchers have been playing with AI ‘consciousness.’ What they found was unexpectedfastcompany.com · Sep 15, 2026
- Google Researchers Have Been Playing with AI ‘Consciousness’ - Ohio Society of Association Professionalsohiosap.org · Sep 17, 2026
Machine-generated summary based on the titles and excerpts of the source articles. The facts come from the linked article.